layoutlmv2_docvqa_first

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.2992

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
3.7028	0.1106	50	4.0813
3.4589	0.2212	100	3.4851
3.7528	0.3319	150	3.6317
3.7319	0.4425	200	3.2309
3.3752	0.5531	250	3.6393
3.526	0.6637	300	3.1241
3.0934	0.7743	350	3.1827
3.0028	0.8850	400	2.7205
2.7686	0.9956	450	2.5475
2.2514	1.1062	500	2.9350
2.2214	1.2168	550	2.5100
2.1205	1.3274	600	2.4464
2.2802	1.4381	650	2.3872
2.0615	1.5487	700	2.3451
2.0007	1.6593	750	2.2994
2.005	1.7699	800	2.6729
1.9238	1.8805	850	2.2630
1.8631	1.9912	900	2.2992

Framework versions

• Transformers 4.44.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1